Intelligent voice broadcast assistant selection method and system

[0027] The invention discloses a method for selecting an intelligent voice broadcast assistant, referring to figure 1 , including the following steps:

[0028] S1. Collect user voice. Specifically, the voice of the user is collected through a recording device, such as a microphone array, and the quality of the collected audio is improved through processing such as noise suppression, echo cancellation, and voice enhancement.

[0029] S2. Use the neural network to classify users according to gender and age, and obtain classification labels corresponding to user voices;

[0030] S3. Based on the method of big data statistics, analyze the preferences of people corresponding to different classification labels for different voice assistants, and use the voice assistant suitable for the current classification label to broadcast according to the statistical results. The differences between different voice assistants include timbre and avatar, the voice of the selected timbre is played

[0035] refer to figure 2 , The invention discloses an intelligent voice broadcast assistant selection system, including a voice collection module, a user classification module, and a voice assistant selection module.

[0036] Among them, the user classification module is used to use the neural network to classify users according to gender and age, and obtain classification labels corresponding to user voices. The classification labels include child male, child female, young male, young female, elderly male, and elderly female.

[0037] The voice assistant selection module is used to analyze the preferences of people corresponding to different classification labels for different voice assistants based on the method of big data statistics, and use the voice assistant suitable for the current classification label to broadcast according to the statistical results.

[0038] The voice assistant selection module includes a timbre selection module and an avatar selection module, and the